使用 tf.data 加载 NumPy 数据

在 Tensorflow.org 上查看 在 Google Colab 运行 在 Github 上查看源代码 下载此 notebook

本教程提供了将数据从 NumPy 数组加载到 tf.data.Dataset 的示例 本示例从一个 .npz 文件中加载 MNIST 数据集。但是,本实例中 NumPy 数据的来源并不重要。

安装

 
import numpy as np
import tensorflow as tf
import tensorflow_datasets as tfds

.npz 文件中加载

DATA_URL = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz'

path = tf.keras.utils.get_file('mnist.npz', DATA_URL)
with np.load(path) as data:
  train_examples = data['x_train']
  train_labels = data['y_train']
  test_examples = data['x_test']
  test_labels = data['y_test']

使用 tf.data.Dataset 加载 NumPy 数组

假设您有一个示例数组和相应的标签数组,请将两个数组作为元组传递给 tf.data.Dataset.from_tensor_slices 以创建 tf.data.Dataset

train_dataset = tf.data.Dataset.from_tensor_slices((train_examples, train_labels))
test_dataset = tf.data.Dataset.from_tensor_slices((test_examples, test_labels))

使用该数据集

打乱和批次化数据集

BATCH_SIZE = 64
SHUFFLE_BUFFER_SIZE = 100

train_dataset = train_dataset.shuffle(SHUFFLE_BUFFER_SIZE).batch(BATCH_SIZE)
test_dataset = test_dataset.batch(BATCH_SIZE)

建立和训练模型

model = tf.keras.Sequential([
    tf.keras.layers.Flatten(input_shape=(28, 28)),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax')
])

model.compile(optimizer=tf.keras.optimizers.RMSprop(),
                loss=tf.keras.losses.SparseCategoricalCrossentropy(),
                metrics=[tf.keras.metrics.SparseCategoricalAccuracy()])
model.fit(train_dataset, epochs=10)
Epoch 1/10
938/938 [==============================] - 2s 2ms/step - loss: 3.0529 - sparse_categorical_accuracy: 0.8668
Epoch 2/10
938/938 [==============================] - 2s 2ms/step - loss: 0.5263 - sparse_categorical_accuracy: 0.9247
Epoch 3/10
938/938 [==============================] - 2s 2ms/step - loss: 0.3805 - sparse_categorical_accuracy: 0.9420
Epoch 4/10
938/938 [==============================] - 2s 2ms/step - loss: 0.3124 - sparse_categorical_accuracy: 0.9527
Epoch 5/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2849 - sparse_categorical_accuracy: 0.9584
Epoch 6/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2546 - sparse_categorical_accuracy: 0.9622
Epoch 7/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2362 - sparse_categorical_accuracy: 0.9663
Epoch 8/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2163 - sparse_categorical_accuracy: 0.9693
Epoch 9/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2087 - sparse_categorical_accuracy: 0.9710
Epoch 10/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2046 - sparse_categorical_accuracy: 0.9727

<tensorflow.python.keras.callbacks.History at 0x7f39bb45ed68>
model.evaluate(test_dataset)
157/157 [==============================] - 0s 1ms/step - loss: 0.6024 - sparse_categorical_accuracy: 0.9542

[0.6023730039596558, 0.954200029373169]